给一篇文章,里面是由一个个单词组成,单词中间空格隔开,再给一个字符串指针数组,比如 char *str[]={"hello","world","good"};
求文章中包含这个字符串指针数组的最小子串。注意,只要包含即可,没有顺序要求。
提示:文章也可以理解为一个大的字符串数组,单词之前只有空格,没有标点符号。
#include <stdio.h>
#include <stdlib.h>
/*
*截取字符串
*/
char* subString(char *src, int pos, int len) {
char *p = src;
char *substr = (char*) calloc(sizeof(char), len + 1);
int i = 0;
p += pos;
while (len--) {
substr[i++] = *(p++);
}
substr[i] = '\0';
return substr;
}
int* getIndexs(char *content, char* search[], int searchSize) {
int i = 0;
int rear = 0, front = 0;
int contentSize = strlen(content);
int* hash = calloc(sizeof(int), contentSize);
for (i = 0; i < contentSize; i++) {
hash[i] = -1;
}
i = 0;
int myLen = strlen(search[i++]);
int maxLen = myLen, minLen = myLen;
i = 0;
while (i < searchSize) {
myLen = strlen(search[i++]);
minLen = minLen > myLen ? myLen : minLen;
maxLen = maxLen < myLen ? myLen : maxLen;
}
while (rear <= contentSize) {
if (*(content + rear) == ' ' || *(content + rear) == '\0') {
int difLen = rear - front;
//单词长度在区间内
if (difLen <= maxLen && difLen >= minLen) {
for (i = 0; i < searchSize; i++) {
if (!strcmp(search[i], subString(content, front, difLen))) {
hash[front] = i;
}
}
}
rear += 1;
front = rear;
} else {
rear++;
}
}
return hash;
}
char* getStrByArrage(char* content, int begin, int end) {
char* p = content + end;
int rear = end;
while (*(p++) != ' ') {
rear++;
}
return subString(content, begin, rear - begin);
}
char* findMinSubString(char* content, char* search[], int rows) {
int contentSize = strlen(content);
int* hash = getIndexs(content, search, rows);
int i;
/*for (i = 0; i < contentSize; ++i) {
if (hash[i] != -1)
printf("front:%3d, searchId:%3d", i, hash[i]);
}*/
//当前范围下搜索字出现次数
int appearNum[rows];
for (i = 0; i < rows; i++) {
appearNum[i] = 0;
}
//起止游标
int prev = 0, end = 0;
//最小长度
int minLen = 2100000000;
//最小的起止下标
int minPrev = 0, minEnd = 0;
//已出现的搜索词数量
int count = 0;
while (end < contentSize || count == rows) {
//prev,end不包含所有关键字,扩大范围
if (count < rows) {
if (hash[end] != -1) {
if (appearNum[hash[end]] == 0) {
count++;
}
appearNum[hash[end]]++;
}
end++;
}
//包含所有关键字,缩小范围
if (count == rows) {
if (end - prev < minLen) {
minPrev = prev;
minEnd = end - 1;
minLen = end - prev;
}
if (hash[prev] != -1) {
appearNum[hash[prev]]--;
if (appearNum[hash[prev]] == 0) {
count--;
}
}
prev++;
}
}
return getStrByArrage(content, minPrev, minEnd);
}
int main(void) {
//文章内容
char* content =
"hello good world kitty my world is a hello good a world hello space";
char *search[] = { "hello", "world", "good" };
int rows = sizeof(search) / sizeof(char*);
int contentSize = strlen(content);
puts(findMinSubString(content, search, rows));
return EXIT_SUCCESS;
}